In the synthesis of pharmaceutical intermediates, concentration is commonly employed to separate the product and recycle the solvents. To achieve a cost-effective manufacturing, operating parameters shall be adjusted over time, which could traditionally be achieved based on dynamic simulation, but with significant computation cost. In this work, we introduced a Bayesian optimization approach to design the optimal operating condition of a pharmaceutical intermediate in the production of Lamivudine. Using a Gaussian process regression as the surrogate model, the approach tremendously reduced the computational cost in searching for the optimal design. In comparison to other commonly used intelligent optimization algorithms, the results demonstrate that the presented approach confers evident advantages, especially in reducing the tendency of getting trapped in local optima and in improving the speed of convergence to an optimal solution.